Meta AI helps build experimental catalyst database

A combination of AI and advanced materials testing has been used to rapidly create an open-source database of electrocatalysts that could be vital to the energy transition.  

Known as Open Catalyst Experiments 2024 (OCx24), the research was carried out by Meta, VSParticle (VSP) and the University of Toronto. Over the course of just a few months, the project saw 525 catalyst materials identified, synthesised and tested. It’s claimed the materials could play a key role in areas such as carbon capture, hydrogen production and battery chemistry.  

Meta’s Fundamental AI Research (FAIR) team has been working on speeding up the discovery of electrocatalysts, but the large and diverse datasets needed for AI to work effectively are not available. OCx24 sought to address this issue to some degree, creating an open-source database that can help bridge the data gap.

“Through this collaboration, we’re breaking new ground in material discovery,” said Larry Zitnick, research director at Meta AI.

“It marks a significant leap in our ability to predict and validate materials that are critical for clean energy solutions. The results we’re seeing with electrocatalysts demonstrate the real-world potential of AI in addressing urgent climate challenges.” 

Register now to continue reading

Thanks for visiting The Engineer. You’ve now reached your monthly limit of news stories. Register for free to unlock unlimited access to all of our news coverage, as well as premium content including opinion, in-depth features and special reports.  

Benefits of registering

  • In-depth insights and coverage of key emerging trends

  • Unrestricted access to special reports throughout the year

  • Daily technology news delivered straight to your inbox